Neural 3D reconstruction from sparse views using geometric priors  

作　　者：Tai-Jiang Mu Hao-Xiang Chen Jun-Xiong Cai Ning Guo 

机构地区：[1]BNRist,Department of Computer Science and Technology,Tsinghua University,Beijing 100084,China [2]Academy of Military Sciences,Beijing 100091,China

出　　处：《Computational Visual Media》2023年第4期687-697,共11页计算可视媒体（英文版）

基　　金：supported by the National Natural Science Foundation of China(Grant No.61902210).

摘　　要：Sparse view 3D reconstruction has attracted increasing attention with the development of neural implicit 3D representation.Existing methods usually only make use of 2D views,requiring a dense set of input views for accurate 3D reconstruction.In this paper,we show that accurate 3D reconstruction can be achieved by incorporating geometric priors into neural implicit 3D reconstruction.Our method adopts the signed distance function as the 3D representation,and learns a generalizable 3D surface reconstruction model from sparse views.Specifically,we build a more effective and sparse feature volume from the input views by using corresponding depth maps,which can be provided by depth sensors or directly predicted from the input views.We recover better geometric details by imposing both depth and surface normal constraints in addition to the color loss when training the neural implicit 3D representation.Experiments demonstrate that our method both outperforms state-of-the-art approaches,and achieves good generalizability.

关 键 词：sparse views 3D reconstruction volume rendering geometric priors neural implicit 3D representation 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]